2021 Summer School
For Q&A, please visit https://ai-security.github.io/summer-school-2021/qna.html.
Theme: Advances and Challenges of Artificial Intelligence in the Internet-of-Things Era
Internet-of-Things (IoT) is a paradigm shifting technology that advances various aspects in our life in recent
years. The proliferation of Artificial Intelligence (AI) opens up the possibility of integrating intelligence into
various IoT devices, which creates many smart and efficient solutions in areas such as healthcare, security
surveillance, self-drive car, human activity recognition, transportation, robots in manufacturing, and risk
management to name a few. The IoT devices range from high-end computers to mobile devices and low-
end microcontroller, wherein many of them are resource-constrained in computation power and storage.
Due to this reason, it is challenging to apply deep learning (mostly computationally extensive and requiring
high storage space) into resource-constrained IoT devices. To address these challenges, various
approaches have been proposed to make deep learning lightweight and optimized for resource-
constrained devices. In this workshop, we will review and discuss the representative techniques on the
hardware level (hardware acceleration techniques) as well as on the software level (model compression
techniques). We will also deal with the fundamental aspects of reinforcement learning, challenges and
progresses in face recognition, biometric applications and federated learning. Interesting research areas
are presented to design future networks based on AI.
Date: 15-16 July, 2021
Venue: Virtual event
Program Committee Chair:
Prof. Seong Oun Hwang (Gachon University, South Korea)
Program Committee:
Prof. Hyung Jin Chang (University of Birmingham, United Kingdom)
Prof. Byung Chul Ko (Keimyung University, South Korea)
Dr. Boon-Yaik Ooi (Universiti Tunku Abdul Rahman, Malaysia)
Prof. Andrew Beng-Jin Teoh (Yonsei University, South Korea)
Dr. Wai Kong Lee (Gachon University, South Korea)
Prof. Soohyun Park (Kookmin University, South Korea)
Prof. Byung Seo Kim (Hongik University, South Korea)
Prof. Hyunsik Ahn (Tongmyong University, South Korea)
Prof. JeongYon Shim (Kangnam University, South Korea)
Co-host:
Institute of Electronics and Information Engineers
IEEE Seoul Section Sensors Council Chapter
Gachon University BK21 FAST Artificial Intelligence Convergence Center
Hongik University Research Team for Super-Distributed Autonomous Computing Service Technologies
Kookmin University Special Communication & Convergence Service Research Center
Program Schedule:
15 July 2021
Time
Program
Speaker
09:30 –
10:20
Reinforcement Learning and Stochastic Optimization: A
unified framework for sequential decisions Part 1
Prof. Warren Powell,
Princeton University, USA
10:20 –
11:00
New Challenges to Face Recognition: Low-Resolution Face
Recognition and Periocular Recognition
Dr. Cheng-Yaw Low, Yonsei
University, Korea
11:00 –
11:40
AI for Information-Centric Networks as a Future Network
Technology
Prof. Byung Seo Kim,
Hongik University, Korea
11:40 –
12:20
Deep Review of Model Compression in Knowledge
Distillation Side
Prof. Byung Chul Ko,
Keimyung University, Korea
12:20 –
14:00
Lunch break
14:00 -
14:40
Biometric Cryptosystem: Progress and Challenge
Prof. Andrew Beng-Jin
Teoh, Yonsei University,
Korea
14:40 –
15:20
Maritime, Underwater IoT and AI-based First-order logic
TUM-IoT Digtital Twin
* TUM-IoT : Terristrial, Underwater, Maritime - IoT
Prof. Soohyun Park,
Kookmin University, Korea
15:20
End
16 July 2021
Time
Program
Speaker
09:30 –
10:20
Reinforcement Learning and Stochastic Optimization: A
unified framework for sequential decisions Part 2
Prof. Warren Powell,
Princeton University, USA
10:20 –
11:00
Overview of Model Compression and Quantization in Deep
Learning
Dr. Jin-Chuan See,
Universiti Tunku Abdul
Rahman, Malaysia
11:00 –
11:40
Edge Federated Learning: Recent Advances and Open
Research Problems
Dr. Rehmat Ullah, Queen's
University, UK
11:40 –
12:20
Hardware Acceleration and Optimization of Deep Neural
Networks
Prof. William Song, Yonsei
University, Korea
12:20
End
Synopses:
Speaker
Synopsis
Prof. Warren Powell,
Princeton University,
USA
Reinforcement Learning and Stochastic Optimization: A unified framework
for sequential decisions Part 1 & 2
*Associated online books are available at
http://castlelab.princeton.edu/RLSO/ and
http://tinyurl.com/sequentialdecisionanalytics. Python modules are
available at https://github.com/wbpowell328/stochastic-optimization that
illustrate the ideas in a number of applications.
I am going to provide a single,
unified framework that covers every
sequential decision problem,
ranging from pure learning
problems (e.g. running
experiments), to complex dynamic
resource allocation problems, or
stochastic search problems. All of
the problems reduce to optimizing
over “policies” which are methods
for making decisions. I will identify
four (meta) classes of policies that
include every method studied in the
academic literature, or used in
practice. Each of the four classes of
policies will be illustrated in the context of pure learning problems,
stochastic search, and a variety of applications in transportation, energy and
health.
Dr. Cheng-Yaw Low,
Yonsei University, Korea
New Challenges to Face Recognition: Low-Resolution Face Recognition and
Periocular Recognition
Face recognition has continually accomplished significant breakthroughs
thanks to the advancement of deep neural networks (DNN) in association
with powerful loss functions and the availability of million-scale training
datasets. In place of the typical face recognition problem, this talk
emphasizes two new challenges to face recognition, specifically low-
resolution (LR) face recognition and periocular face recognition (masked
face recognition). We will probe into the major problems for training a high-
capacity DNN to confront these challenges. In the meantime, some recent
works will also be introduced.
Prof. Byung Seo Kim,
Hongik University, Korea
AI for Information-Centric Networks as a Future Network Technology
Even though designed for future network Internet technology, Information
Centric Networking (ICN) has been researched for wireless communications
because it provides connectionless, non-destination-oriented, caching, etc.
Particularly, ICN is well-adopted for massive, content-based, heterogeneous
IoT networks. Recently, AI-based ICNs are studied to overcome the issues of
ICNs such as optimal forwarding & routing, caching strategy, congestion
control, producer mobility, etc. In this talk, after a brief review of ICNs and
the issues of ICNs in wired & wireless networks, recent researches for AI-
based ICNs are introduced.
Prof. Byung Chul Ko,
Keimyung University,
Korea
Deep Review of Model Compression in Knowledge Distillation Side
Deep learning algorithms have higher performance as the layers deepen,
but have disadvantages in that memory requirements and processing speed
increase as they require many parameters. Therefore, recently, AI studies
have been attempted to achieve similar performance while reducing the
number of deep learning layers and parameters. Among these methods,
there are parameter pruning and sharing, low-rank approximation, and
teacher-student networks. In this lecture, each deep learning compression
technique will be briefly reviewed, and in particular, the teacher-student
networks method will be described in focus. In addition, I will introduce
cases in which these compression methods are actually applied.
Prof. Andrew Beng-Jin
Teoh, Yonsei University,
Korea
Biometric Cryptosystem: Progress and Challenge
The inability of humans to remember and generate strong secrets makes it
problematic for people to manage cryptographic keys. To address this
problem, biometric cryptosystem has been put forward to enable a user to
repeatedly generate a cryptographic key from his/her biometrics while
protecting identity theft. Some prominent instances of biometric
cryptosystems are Fuzzy Commitment, Fuzzy Vault and Fuzzy Extractor.
Despite biometric cryptosystems have made vital contributions by
specifying formal security definitions with where the schemes can be
analyzed and provably secure, there remains a huge gap between
theoretical soundness and practical systems. In this talk, an overview of
progress of biometric cryptosystems will be presented. Specifically, design
requirements, pitfalls and subtleties that are commonly overlooked in the
practical design and assessment of biometric cryptosystems will be
highlighted. Finally, a number of possible remedies addressing the
challenges in designing practical biometric cryptosystems are discussed.
Prof. Soohyun Park,
Kookmin University,
Korea
Maritime, Underwater IoT and AI-based First-order logic TUM-IoT Digital
Twin
In order to actively respond to changes in the Internet of Service (IoS)
market environment of the Internet of Things (IoT) that exists in the
terrestrial / underwater / maritime domain, a key technology for creating
an intelligent autonomous service based on situational awareness is
required. By combining intelligent underwater and terrestrial IoS
interworking services with digital twin technology, it is necessary to provide
standard technology that can autonomously create optimal services,
thereby providing digitalization services at low cost. It is possible to
autonomously create new intelligent services by linking IoS of various IoT in
different domains (underwater/sea/terrestrial) according to context.
Dr. Jin-Chuan See,
Universiti Tunku Abdul
Rahman, Malaysia
Overview of Model Compression and Quantization in Deep Learning
Image classification using deep learning is a powerful technique and was
shown to produce higher accuracy in recent years. However, high accuracy
deep learning networks typically contains large network parameter sizes.
This presents an issue when it comes to porting onto resource constrained
(in terms of energy, availability CPU/GPU and memory sizes) devices. Model
compression techniques was proposed to reduce the large network
parameter sizes and at the same time retains the networks’ accuracy. In this
session, we first give an overview of the techniques used in model
compression, followed by an in-depth discussion on one of the techniques,
quantization.
Dr. Rehmat Ullah,
Queen's University, UK
Edge Federated Learning: Recent Advances and Open Research Problems
Google recently introduced the concept of Federated Learning (FL) in 2016,
which is a privacy-preserving ML technique in which an ML model is
collaboratively learned across several distributed devices (e.g., mobile
phones), while all training data is kept on local devices. The FL provides
privacy-by-design and is well suited for edge computing applications
because it can take advantage of the computation power of edge servers.
This talk will discuss distributed ML, with a focus on FL for edge computing
systems. This talk will start by giving a quick explanation of FL, how FL solves
the data island problem in IoT and state-of-art advances of FL. The edge
federated learning applications with open-source platforms, current trends,
and recent development will be discussed particularly form the network
perspective. Furthermore, open research challenges with potential
solutions will be presented.
Prof. William Song,
Yonsei University, Korea
Hardware Acceleration and Optimization of Deep Neural Networks
Nearing the end of Moore’s Law, computing systems are geared towards
specialization, i.e., executing workloads using multiple, heterogeneous
processing units. With rapid advances in deep learning techniques, deep
neural networks (DNNs) have become important workloads for the
computer systems. Such trends sparked recent races to develop neural
processing units (NPU), specialized processors for DNNs. This talk discusses
various recent efforts to design lightweight neural networks and
optimization techniques built into hardware accelerators to enhance
computational efficiency. In many cases, software-level optimization ideas
for DNN acceleration are tightly coupled with hardware-level supports. A
review of hardware-side related work will hopefully be helpful to a large
audience of the event.
Registration:
The registration site is https://www.theieie.org/events/?tab=4&part=02&c_id=747.
Registration must be completed no later than 14 July 2021.
A registration includes electronic presentation materials, but not lunch.
Please send your inquiries about the registration to sohwang at gachon dot ac dot kr.
Students
Professionals
150,000 KRW
300,000 KRW
